Standard test image

About: Standard test image is a research topic. Over the lifetime, 5217 publications have been published within this topic receiving 98486 citations.

Efficient classifier generation and weighted voting for atlas-based segmentation: two small steps faster and closer to the combination oracle

Abstract: Atlas-based segmentation has proven effective in multiple applications. Usually, several reference images are combined to create a representative average atlas image. Alternatively, a number of independent atlas images can be used, from which multiple segmentations of the image of interest are derived and later combined. One of the major drawbacks of this approach is its large computational burden caused by the high number of required registrations. To address this problem, we introduce One Registration, Multiple Segmentations (ORMS), a procedure to obtain multiple segmentations with a single online registration. This can be achieved by pre-computing intermediate transformations from the initial atlas images to an average image. We show that, compared to the usual approach, our method reduces time considerably with little or no loss in accuracy. On the other hand, optimum combination of these segmentations remains an unresolved problem. Different approaches have been adopted, but they are all far from the upper bound of any combination strategy. This is given by the Combination Oracle, which classifies a voxel correctly if any individual segmentation coincides with the ground truth. We present here a novel combination approach, based on weighting the different segmentations according to the mutual information between the test image and the atlas image after registration. We compare this method with other existing combination strategies using microscopic MR images of mouse brains, achieving statistically significant improvement in segmentation accuracy.

Method and apparatus for real time image recognition

Abstract: Method and apparatus for real time recognition of test images by comparison with sample images. The test image to be recognized is scanned to produce a plurality of analog signals of the luminance levels. These luminance signals are screened to eliminate background signals and are converted to digital signals. A distribution function of the occurrence frequency versus the luminance level is determined from the test image signals. Typical parameters of said distribution function are calculated and compared with sets of stored corresponding parameters derived in a similar manner from known reference sample images. A recognition signal is outputted to indicate the sample image which most closely resembles the test image as determined by said comparison, provided that the quantitatively determined differences between test and sample images are below a predetermined threshold value.

A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning

Abstract: Prevalent techniques in zero-shot learning do not generalize well to other related problem scenarios. Here, we present a unified approach for conventional zero-shot, generalized zero-shot and few-shot learning problems. Our approach is based on a novel Class Adapting Principal Directions (CAPD) concept that allows multiple embeddings of image features into a semantic space. Given an image, our method produces one principal direction for each seen class. Then, it learns how to combine these directions to obtain the principal direction for each unseen class such that the CAPD of the test image is aligned with the semantic embedding of the true class, and opposite to the other classes. This allows efficient and class-adaptive information transfer from seen to unseen classes. In addition, we propose an automatic process for selection of the most useful seen classes for each unseen class to achieve robustness in zero-shot learning. Our method can update the unseen CAPD taking the advantages of few unseen images to work in a few-shot learning scenario. Furthermore, our method can generalize the seen CAPDs by estimating seen-unseen diversity that significantly improves the performance of generalized zero-shot learning. Our extensive evaluations demonstrate that the proposed approach consistently achieves superior performance in zero-shot, generalized zero-shot and few/one-shot learning problems.

MAP Disparity Estimation Using Hidden Markov Trees

Abstract: A new method is introduced for stereo matching that operates on minimum spanning trees (MSTs) generated from the images. Disparity maps are represented as a collection of hidden states on MSTs, and each MST is modeled as a hidden Markov tree. An efficient recursive message-passing scheme designed to operate on hidden Markov trees, known as the upward-downward algorithm, is used to compute the maximum a posteriori (MAP) disparity estimate at each pixel. The messages processed by the upward-downward algorithm involve two types of probabilities: the probability of a pixel having a particular disparity given a set of per-pixel matching costs, and the probability of a disparity transition between a pair of connected pixels given their similarity. The distributions of these probabilities are modeled from a collection of images with ground truth disparities. Performance evaluation using the Middlebury stereo benchmark version 3 demonstrates that the proposed method ranks second and third in terms of overall accuracy when evaluated on the training and test image sets, respectively.